Research Area:  Machine Learning
Generating semantically coherent responses is still a major challenge in dialogue generation. Different from conventional text generation tasks, the mapping between inputs and responses in conversations is more complicated, which highly demands the understanding of utterance-level semantic dependency, a relation between the whole meanings of inputs and outputs. To address this problem, we propose an Auto-Encoder Matching (AEM) model to learn such dependency. The model contains two auto-encoders and one mapping module. The auto-encoders learn the semantic representations of inputs and responses, and the mapping module learns to connect the utterance-level representations. Experimental results from automatic and human evaluations demonstrate that our model is capable of generating responses of high coherence and fluency compared to baseline models.
Keywords:  
Auto-Encoder Matching Model
Dialogue Generation
Machine Learning
Deep Learning
Author(s) Name:  Liangchen Luo, Jingjing Xu, Junyang Lin, Qi Zeng, Xu Sun
Journal name:  Computation and Language
Conferrence name:  
Publisher name:  arxiv
DOI:  arXiv:1808.08795
Volume Information:  
Paper Link:   https://arxiv.org/abs/1808.08795